Freight insurance pricing strategy based on an online freight platform

Abstract

Purpose

The development of digital technology has provided technical support to various industries. Specifically, Internet-based freight platforms can ensure the high-quality development of the logistics industry. Online freight platforms can use cargo transportation insurance to improve their service capabilities, promote their differentiated development, create products with platform characteristics and increase their core competitiveness.

Design/methodology/approach

This study uses a generalised linear model to fit the claim probability and claim intensity data and analyses freight insurance pricing based on the freight insurance claim data of a freight platform in China.

Findings

Considering traditional pricing risk factors, this study adds two risk factors to fit the claim probability data, that is, the purchase behaviour of freight insurance customers and road density. The two variables can significantly influence the claim probability, and the model fitting outcomes obtained with the logit connection function are excellent. In addition, this study examines the model results under various distribution types for the fitting of the claim intensity data. The fitting outcomes under a gamma distribution are superior to those under the other distribution types, as measured by the Akaike information criterion.

Originality/value

With actual data from an online freight platform in China, this study empirically proves that a generalised linear model is superior to traditional pricing methods for freight insurance. This study constructs a generalised linear pricing model considering the unique features of the freight industry and determines that the transportation distance, cargo weight and road density have a significant influence on the claim probability and claim intensity.

Citation

Yang, C., Chen, L. and Xia, Q. (2023), "Freight insurance pricing strategy based on an online freight platform", Industrial Management & Data Systems, Vol. 123 No. 11, pp. 2929-2945. https://doi.org/10.1108/IMDS-05-2023-0307